© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 8600
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical expressions and related adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    еÑĢап
    -0.14
    ãĤ¾
    -0.14
    梨
    -0.14
     pione
    -0.14
    Insets
    -0.14
    oola
    -0.13
    à¸ļาย
    -0.13
     jednak
    -0.13
    ofilm
    -0.13
    Ùĥت
    -0.13
    POSITIVE LOGITS
    )
    0.16
    ãĢĭçļĦ
    0.15
    å¢
    0.15
    )ìĿĺ
    0.15
    ),
    0.14
    rame
    0.14
    ï¼īãģ®
    0.14
    ÄĻd
    0.14
    gle
    0.13
    unos
    0.13
    Activations Density 0.133%

    No Known Activations